EP3382597A1 - Amélioration de référence des données biométriques - Google Patents

Amélioration de référence des données biométriques Download PDF

Info

Publication number
EP3382597A1
EP3382597A1 EP17305377.8A EP17305377A EP3382597A1 EP 3382597 A1 EP3382597 A1 EP 3382597A1 EP 17305377 A EP17305377 A EP 17305377A EP 3382597 A1 EP3382597 A1 EP 3382597A1
Authority
EP
European Patent Office
Prior art keywords
minutiae
biometric
user
stored
enrich
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP17305377.8A
Other languages
German (de)
English (en)
Inventor
Nicolas LE SAUX
Ali Zeamari
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Thales DIS France SA
Original Assignee
Gemalto SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Gemalto SA filed Critical Gemalto SA
Priority to EP17305377.8A priority Critical patent/EP3382597A1/fr
Publication of EP3382597A1 publication Critical patent/EP3382597A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1365—Matching; Classification
    • G06V40/1371—Matching features related to minutiae or pores
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/993—Evaluation of the quality of the acquired pattern
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/50—Maintenance of biometric data or enrolment thereof

Definitions

  • the present invention relates to a device having a biometric sensor to acquire biometric minutiae from a user of the device, said device having a stored minutiae reference for this user and a comparator to compare the acquired biometric minutiae with the minutiae reference and to authenticate the user as soon as the comparison is above a matching threshold.
  • the invention also pertains to a method to enrich biometric minutiae and manage evolution of minutiae reference.
  • any kind of biometric authentication comprises an enrolment phase where minutiae are acquired before any authentication to be performed. Such minutiae acquired during the enrollment phase are stored in the device for later authentication. Any matching of acquired biometric data in comparison with the stored minutiae reference.
  • the enrolment procedure requires that the user presents different times its biometric data, i.e. eyes, fingerprint, voice... Once done, a resulting minutiae reference is stored in the device. Then the acquired minutia or data are compared using a matching algorithm based on a comparison algorithm that compares extracted data, minutia or raw data, to the stored minutiae reference. If the result of the comparison is above a predetermined threshold the user is authenticated.
  • minutiae references are thus static. Once enrolled, the user does not have possibility to modify the minutiae reference. Security is of course at stake. The possibility to modify at willing the minutiae reference would of course ruin any interest of the biometric method and is not at all investigated by any of the current biometric devices manufacturers.
  • the present invention proposes a breakthrough approach in terms of minutiae reference.
  • the present invention is defined, in its broadest sense, as a device having a biometric sensor to acquire biometric minutiae from a user of the device, said device having a stored minutiae reference for this user and a comparator to compare the acquired biometric minutiae with the minutiae reference and to authenticate the user as soon as the comparison is above a matching threshold, the device being characterized in that it comprises an enrichment module to detect a successful authentication, and upon successful authentication, to inspect the corresponding acquired biometric minutiae for relevant minutiae not known in the minutiae reference and to add or modify such relevant minutiae to the stored minutiae reference to enrich it.
  • the invention breaks the prejudices of static minutiae references by proposing to modify the minutiae references directly on the field.
  • the purpose of this invention is indeed to continuously enrich the stored data upon successful authentication when of good quality.
  • the minutia references are thus continuously enriched with recent data from the user and allows to manage the evolution of the minutiae.
  • the method bypasses the static minutiae limitation bay allowing to enrich minutiae with recent acquired minutiae after a successful authentication.
  • This invention allows to manage the evolution of the minutiae. This could bring some benefits in some particular use cases such as evolution of minutiae due to aging, especially for children, and management of alteration of biometric data due to scars for instance.
  • This invention allows also to enrich an already acquired minutiae by adding missing parts. This acquisition allows to increase the user experience.
  • Such an auto-learning could be particularly valuable it at least two main situations as it enables to manage the evolution of biometric data of the user for example in case of a wound causing a scar or any other cause of a change on a minutia..
  • the invention also enables to enrich the area of minutia, for example for fingerprint by adding area that where not acquired during the initial enrolment in order to increase rate of successful recognition.
  • the minutia are continuously enriched with recent data from the user and the invention thus allows to manage the evolution of the minutiae which is not the case in the state-of-the-art solutions.
  • the invention is a way to improve user experience by increasing the rate of good matching. In fact, a better quality of extracted data is obtained and so less reject are observed and a better user experience is obtained.
  • the enrichment module uses for enrichment the acquired biometric minutiae only when the authentication has reached a predetermined quality level.
  • This embodiment enables to select authentications of good quality only to enrich the minutiae reference as stored. It filters the weak quality authentication where wrong minutiae could be introduced in the stored minutiae reference.
  • the comparator is adapted to increase the matching threshold in relation with the evolution of the stored minutiae reference.
  • This feature enables to increase the quality of the authentication by increasing the matching threshold as far as the quality of the minutiae reference increases. It indeed allows to increase the threshold when enough data are acquired for the minutiae reference.
  • the enrichment module allocates more weight to recently acquired biometric minutiae in the stored minutiae reference.
  • This feature is particularly adapted to situations where a scar appears among the minutiae of the user or where the user is a child and grows.
  • the present invention also relates to a method to enrich minutiae reference as stored in a device having a biometric sensor to acquire biometric minutiae from a user of the device and a comparator to compare in a comparison step the acquired biometric minutiae with the minutiae reference and to authenticate the user as soon as the comparison is above a matching threshold, said method comprising, upon successful authentication, the step of inspecting the corresponding acquired biometric minutiae for relevant minutiae not known in the minutiae reference and the step of adding or modifying such relevant minutiae to the stored minutiae reference to enrich it.
  • FIG. 1 schematically shows a device D of the invention.
  • This device D comprises having a biometric sensor BS to acquire biometric minutiae BM from a user of the device D.
  • the device D also has a memory MEM in which a minutiae reference MR is stored for this user.
  • a comparator COMP in device D then compares the acquired biometric minutiae BM with the minutiae reference MR. As generally implemented in such comparator according to the state of the art, the comparison is evaluated and quantified and the user is then authenticated as soon as the comparison is above a matching threshold.
  • the device D comprises an enrichment module ENRM.
  • This enrichment module ENRM is adapted to detect a successful authentication SA by the comparator COMP.
  • the enrichment module ENRM inspect the corresponding acquired biometric minutiae BM for relevant minutiae RM not known in the minutiae reference MR.
  • the enrichment module is further adapted to add or modify such relevant minutiae RM to the stored minutiae reference MR to enrich it.
  • the method of the invention thus comprises a first step S0 of comparison, this comparison resulting in an authentication of not, case Y and N respectively.
  • the invention is active and the enrichment module ENRM inspects the successful authentication SA in step S2.
  • This inspection INSP uses the stored minutia reference MR.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Quality & Reliability (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Collating Specific Patterns (AREA)
EP17305377.8A 2017-03-30 2017-03-30 Amélioration de référence des données biométriques Withdrawn EP3382597A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP17305377.8A EP3382597A1 (fr) 2017-03-30 2017-03-30 Amélioration de référence des données biométriques

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP17305377.8A EP3382597A1 (fr) 2017-03-30 2017-03-30 Amélioration de référence des données biométriques

Publications (1)

Publication Number Publication Date
EP3382597A1 true EP3382597A1 (fr) 2018-10-03

Family

ID=59061939

Family Applications (1)

Application Number Title Priority Date Filing Date
EP17305377.8A Withdrawn EP3382597A1 (fr) 2017-03-30 2017-03-30 Amélioration de référence des données biométriques

Country Status (1)

Country Link
EP (1) EP3382597A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050129290A1 (en) * 2003-12-16 2005-06-16 Lo Peter Z. Method and apparatus for enrollment and authentication of biometric images
US20100060417A1 (en) * 2008-09-05 2010-03-11 Fujitsu Limited Biometrics authentication device and biometrics authentication method
US20100080425A1 (en) * 2008-09-29 2010-04-01 Board of regents of the Nevada System of Higher Education, on Behalf of the University of Minutiae-based template synthesis and matching
EP2624206A1 (fr) * 2010-09-30 2013-08-07 Fujitsu Limited Dispositif d'authentification biométrique, programme d'authentification biométrique et procédé associé
US20130259330A1 (en) * 2012-03-27 2013-10-03 Validity Sensors, Inc. Method of and system for enrolling and matching biometric data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050129290A1 (en) * 2003-12-16 2005-06-16 Lo Peter Z. Method and apparatus for enrollment and authentication of biometric images
US20100060417A1 (en) * 2008-09-05 2010-03-11 Fujitsu Limited Biometrics authentication device and biometrics authentication method
US20100080425A1 (en) * 2008-09-29 2010-04-01 Board of regents of the Nevada System of Higher Education, on Behalf of the University of Minutiae-based template synthesis and matching
EP2624206A1 (fr) * 2010-09-30 2013-08-07 Fujitsu Limited Dispositif d'authentification biométrique, programme d'authentification biométrique et procédé associé
US20130259330A1 (en) * 2012-03-27 2013-10-03 Validity Sensors, Inc. Method of and system for enrolling and matching biometric data

Similar Documents

Publication Publication Date Title
US10223512B2 (en) Voice-based liveness verification
KR101736710B1 (ko) 생체 정보 관리 방법 및 장치
US7929732B2 (en) Methods of identifier determination and of biometric verification and associated systems
JP5560547B2 (ja) 生体認証装置
US20160292408A1 (en) Continuously authenticating a user of voice recognition services
US9667611B1 (en) Situationally aware authentication
CN105260643A (zh) 多指纹交叉解锁方法及系统
US20160034744A1 (en) Fingerprint recognition method and device thereof
US20140007210A1 (en) High security biometric authentication system
WO2012144105A1 (fr) Système d'authentification biométrique
US11042614B2 (en) Authentication device and authentication method
WO2013084617A1 (fr) Système d'authentification biométrique
RU2017110073A (ru) Система аутентификации по отпечатку пальца, программа аутентификации по отпечатку пальца и способ аутентификации по отпечатку пальца
US11611881B2 (en) Integrated systems and methods for passive authentication
US11081115B2 (en) Speaker recognition
KR102261833B1 (ko) 인증 방법 및 장치, 및 인식기 학습 방법 및 장치
CN109063449B (zh) 基于声纹的电子设备解锁方法及相关装置
EP3382597A1 (fr) Amélioration de référence des données biométriques
CN109249898A (zh) 认证装置及认证方法
US7991204B2 (en) Threshold determining device, method and program, and personal authentication system
US8600751B2 (en) Digital method and arrangement for authenticating a person
DE102018220936A1 (de) Verfahren zur Überprüfung eines Sensorwertes eines MEMS-Sensors
KR20190014678A (ko) 사용자에 의한 생체정보 기반의 사용자 인증 레벨 조정 방법
CN114519898A (zh) 生物特征多模态融合识别方法、装置、存储介质及设备
Chaitanya et al. Verification of pattern unlock and gait behavioural authentication through a machine learning approach

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20190404